Files
zephyr-7b-sft-full/trainer_state.json

1570 lines
36 KiB
JSON
Raw Permalink Normal View History

{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 1084,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0009225092250922509,
"grad_norm": 9.1875,
"learning_rate": 1.8348623853211012e-07,
"loss": 1.1392,
"step": 1
},
{
"epoch": 0.004612546125461255,
"grad_norm": 8.5625,
"learning_rate": 9.174311926605506e-07,
"loss": 1.1336,
"step": 5
},
{
"epoch": 0.00922509225092251,
"grad_norm": 4.96875,
"learning_rate": 1.8348623853211011e-06,
"loss": 1.0938,
"step": 10
},
{
"epoch": 0.013837638376383764,
"grad_norm": 2.53125,
"learning_rate": 2.7522935779816517e-06,
"loss": 1.0349,
"step": 15
},
{
"epoch": 0.01845018450184502,
"grad_norm": 2.140625,
"learning_rate": 3.6697247706422022e-06,
"loss": 1.0222,
"step": 20
},
{
"epoch": 0.023062730627306273,
"grad_norm": 1.9765625,
"learning_rate": 4.587155963302753e-06,
"loss": 1.0099,
"step": 25
},
{
"epoch": 0.027675276752767528,
"grad_norm": 2.046875,
"learning_rate": 5.504587155963303e-06,
"loss": 0.9752,
"step": 30
},
{
"epoch": 0.03228782287822878,
"grad_norm": 2.03125,
"learning_rate": 6.422018348623854e-06,
"loss": 0.9981,
"step": 35
},
{
"epoch": 0.03690036900369004,
"grad_norm": 2.15625,
"learning_rate": 7.3394495412844045e-06,
"loss": 1.0022,
"step": 40
},
{
"epoch": 0.04151291512915129,
"grad_norm": 2.09375,
"learning_rate": 8.256880733944956e-06,
"loss": 0.9786,
"step": 45
},
{
"epoch": 0.046125461254612546,
"grad_norm": 2.890625,
"learning_rate": 9.174311926605506e-06,
"loss": 0.9717,
"step": 50
},
{
"epoch": 0.0507380073800738,
"grad_norm": 2.3125,
"learning_rate": 1.0091743119266055e-05,
"loss": 0.9713,
"step": 55
},
{
"epoch": 0.055350553505535055,
"grad_norm": 1.9765625,
"learning_rate": 1.1009174311926607e-05,
"loss": 0.9838,
"step": 60
},
{
"epoch": 0.05996309963099631,
"grad_norm": 2.078125,
"learning_rate": 1.1926605504587156e-05,
"loss": 0.9842,
"step": 65
},
{
"epoch": 0.06457564575645756,
"grad_norm": 3.265625,
"learning_rate": 1.2844036697247708e-05,
"loss": 0.962,
"step": 70
},
{
"epoch": 0.06918819188191883,
"grad_norm": 2.078125,
"learning_rate": 1.3761467889908258e-05,
"loss": 0.9677,
"step": 75
},
{
"epoch": 0.07380073800738007,
"grad_norm": 2.9375,
"learning_rate": 1.4678899082568809e-05,
"loss": 0.96,
"step": 80
},
{
"epoch": 0.07841328413284133,
"grad_norm": 2.890625,
"learning_rate": 1.559633027522936e-05,
"loss": 0.9782,
"step": 85
},
{
"epoch": 0.08302583025830258,
"grad_norm": 2.59375,
"learning_rate": 1.6513761467889912e-05,
"loss": 0.9754,
"step": 90
},
{
"epoch": 0.08763837638376384,
"grad_norm": 2.484375,
"learning_rate": 1.743119266055046e-05,
"loss": 0.9799,
"step": 95
},
{
"epoch": 0.09225092250922509,
"grad_norm": 2.75,
"learning_rate": 1.834862385321101e-05,
"loss": 0.9875,
"step": 100
},
{
"epoch": 0.09686346863468635,
"grad_norm": 3.1875,
"learning_rate": 1.9266055045871563e-05,
"loss": 1.0122,
"step": 105
},
{
"epoch": 0.1014760147601476,
"grad_norm": 2.609375,
"learning_rate": 1.9999948088910656e-05,
"loss": 0.9981,
"step": 110
},
{
"epoch": 0.10608856088560886,
"grad_norm": 2.0,
"learning_rate": 1.9998131257372878e-05,
"loss": 1.0054,
"step": 115
},
{
"epoch": 0.11070110701107011,
"grad_norm": 2.296875,
"learning_rate": 1.999371941029485e-05,
"loss": 0.9882,
"step": 120
},
{
"epoch": 0.11531365313653137,
"grad_norm": 2.234375,
"learning_rate": 1.9986713692771732e-05,
"loss": 1.0127,
"step": 125
},
{
"epoch": 0.11992619926199262,
"grad_norm": 2.140625,
"learning_rate": 1.9977115923137912e-05,
"loss": 0.9851,
"step": 130
},
{
"epoch": 0.12453874538745388,
"grad_norm": 2.5625,
"learning_rate": 1.9964928592495046e-05,
"loss": 1.0177,
"step": 135
},
{
"epoch": 0.12915129151291513,
"grad_norm": 1.828125,
"learning_rate": 1.9950154864065497e-05,
"loss": 1.0139,
"step": 140
},
{
"epoch": 0.13376383763837638,
"grad_norm": 1.828125,
"learning_rate": 1.993279857237133e-05,
"loss": 0.9925,
"step": 145
},
{
"epoch": 0.13837638376383765,
"grad_norm": 1.7578125,
"learning_rate": 1.9912864222239045e-05,
"loss": 0.9819,
"step": 150
},
{
"epoch": 0.1429889298892989,
"grad_norm": 1.96875,
"learning_rate": 1.9890356987630362e-05,
"loss": 1.0336,
"step": 155
},
{
"epoch": 0.14760147601476015,
"grad_norm": 2.078125,
"learning_rate": 1.986528271029931e-05,
"loss": 0.9915,
"step": 160
},
{
"epoch": 0.1522140221402214,
"grad_norm": 1.7421875,
"learning_rate": 1.9837647898276008e-05,
"loss": 0.9992,
"step": 165
},
{
"epoch": 0.15682656826568267,
"grad_norm": 1.7734375,
"learning_rate": 1.9807459724177497e-05,
"loss": 1.0022,
"step": 170
},
{
"epoch": 0.16143911439114392,
"grad_norm": 1.8359375,
"learning_rate": 1.977472602334609e-05,
"loss": 0.9877,
"step": 175
},
{
"epoch": 0.16605166051660517,
"grad_norm": 2.046875,
"learning_rate": 1.973945529181572e-05,
"loss": 1.0017,
"step": 180
},
{
"epoch": 0.1706642066420664,
"grad_norm": 2.015625,
"learning_rate": 1.9701656684106764e-05,
"loss": 1.0078,
"step": 185
},
{
"epoch": 0.1752767527675277,
"grad_norm": 1.734375,
"learning_rate": 1.9661340010850025e-05,
"loss": 0.9911,
"step": 190
},
{
"epoch": 0.17988929889298894,
"grad_norm": 1.796875,
"learning_rate": 1.9618515736240353e-05,
"loss": 0.9972,
"step": 195
},
{
"epoch": 0.18450184501845018,
"grad_norm": 1.671875,
"learning_rate": 1.9573194975320672e-05,
"loss": 0.9998,
"step": 200
},
{
"epoch": 0.18911439114391143,
"grad_norm": 1.8046875,
"learning_rate": 1.952538949109708e-05,
"loss": 0.9921,
"step": 205
},
{
"epoch": 0.1937269372693727,
"grad_norm": 1.78125,
"learning_rate": 1.9475111691485737e-05,
"loss": 0.9759,
"step": 210
},
{
"epoch": 0.19833948339483395,
"grad_norm": 1.828125,
"learning_rate": 1.9422374626092414e-05,
"loss": 0.9886,
"step": 215
},
{
"epoch": 0.2029520295202952,
"grad_norm": 1.7890625,
"learning_rate": 1.936719198282545e-05,
"loss": 1.01,
"step": 220
},
{
"epoch": 0.20756457564575645,
"grad_norm": 1.671875,
"learning_rate": 1.930957808434307e-05,
"loss": 1.0148,
"step": 225
},
{
"epoch": 0.21217712177121772,
"grad_norm": 1.921875,
"learning_rate": 1.9249547884335917e-05,
"loss": 0.9927,
"step": 230
},
{
"epoch": 0.21678966789667897,
"grad_norm": 1.7734375,
"learning_rate": 1.9187116963645845e-05,
"loss": 1.0112,
"step": 235
},
{
"epoch": 0.22140221402214022,
"grad_norm": 1.5859375,
"learning_rate": 1.912230152622189e-05,
"loss": 1.0015,
"step": 240
},
{
"epoch": 0.22601476014760147,
"grad_norm": 1.65625,
"learning_rate": 1.9055118394914545e-05,
"loss": 1.0013,
"step": 245
},
{
"epoch": 0.23062730627306274,
"grad_norm": 1.625,
"learning_rate": 1.898558500710939e-05,
"loss": 0.9996,
"step": 250
},
{
"epoch": 0.235239852398524,
"grad_norm": 1.734375,
"learning_rate": 1.891371941020121e-05,
"loss": 1.0054,
"step": 255
},
{
"epoch": 0.23985239852398524,
"grad_norm": 1.6171875,
"learning_rate": 1.88395402569098e-05,
"loss": 1.0085,
"step": 260
},
{
"epoch": 0.2444649446494465,
"grad_norm": 1.7421875,
"learning_rate": 1.8763066800438638e-05,
"loss": 1.014,
"step": 265
},
{
"epoch": 0.24907749077490776,
"grad_norm": 1.59375,
"learning_rate": 1.868431888947773e-05,
"loss": 1.0142,
"step": 270
},
{
"epoch": 0.253690036900369,
"grad_norm": 1.6953125,
"learning_rate": 1.860331696305188e-05,
"loss": 0.9986,
"step": 275
},
{
"epoch": 0.25830258302583026,
"grad_norm": 2.453125,
"learning_rate": 1.852008204521572e-05,
"loss": 1.0077,
"step": 280
},
{
"epoch": 0.2629151291512915,
"grad_norm": 1.6796875,
"learning_rate": 1.8434635739596945e-05,
"loss": 0.9972,
"step": 285
},
{
"epoch": 0.26752767527675275,
"grad_norm": 1.65625,
"learning_rate": 1.834700022378907e-05,
"loss": 1.0062,
"step": 290
},
{
"epoch": 0.272140221402214,
"grad_norm": 1.71875,
"learning_rate": 1.825719824359524e-05,
"loss": 0.9955,
"step": 295
},
{
"epoch": 0.2767527675276753,
"grad_norm": 1.6015625,
"learning_rate": 1.816525310712456e-05,
"loss": 1.002,
"step": 300
},
{
"epoch": 0.28136531365313655,
"grad_norm": 1.6640625,
"learning_rate": 1.8071188678742457e-05,
"loss": 0.976,
"step": 305
},
{
"epoch": 0.2859778597785978,
"grad_norm": 1.7578125,
"learning_rate": 1.7975029372876706e-05,
"loss": 0.9991,
"step": 310
},
{
"epoch": 0.29059040590405905,
"grad_norm": 1.6875,
"learning_rate": 1.787680014768065e-05,
"loss": 0.9902,
"step": 315
},
{
"epoch": 0.2952029520295203,
"grad_norm": 1.578125,
"learning_rate": 1.777652649855531e-05,
"loss": 0.9902,
"step": 320
},
{
"epoch": 0.29981549815498154,
"grad_norm": 1.7265625,
"learning_rate": 1.7674234451532065e-05,
"loss": 0.9988,
"step": 325
},
{
"epoch": 0.3044280442804428,
"grad_norm": 1.6015625,
"learning_rate": 1.7569950556517566e-05,
"loss": 1.0119,
"step": 330
},
{
"epoch": 0.30904059040590404,
"grad_norm": 1.609375,
"learning_rate": 1.7463701880402738e-05,
"loss": 1.0063,
"step": 335
},
{
"epoch": 0.31365313653136534,
"grad_norm": 1.5859375,
"learning_rate": 1.7355516000037555e-05,
"loss": 0.9962,
"step": 340
},
{
"epoch": 0.3182656826568266,
"grad_norm": 1.65625,
"learning_rate": 1.7245420995073453e-05,
"loss": 1.0047,
"step": 345
},
{
"epoch": 0.32287822878228783,
"grad_norm": 1.609375,
"learning_rate": 1.7133445440675268e-05,
"loss": 0.9797,
"step": 350
},
{
"epoch": 0.3274907749077491,
"grad_norm": 1.578125,
"learning_rate": 1.7019618400104572e-05,
"loss": 0.991,
"step": 355
},
{
"epoch": 0.33210332103321033,
"grad_norm": 1.9453125,
"learning_rate": 1.6903969417176244e-05,
"loss": 0.9942,
"step": 360
},
{
"epoch": 0.3367158671586716,
"grad_norm": 1.71875,
"learning_rate": 1.6786528508590436e-05,
"loss": 0.9841,
"step": 365
},
{
"epoch": 0.3413284132841328,
"grad_norm": 1.6953125,
"learning_rate": 1.666732615614169e-05,
"loss": 1.0075,
"step": 370
},
{
"epoch": 0.3459409594095941,
"grad_norm": 1.5390625,
"learning_rate": 1.6546393298807405e-05,
"loss": 0.9911,
"step": 375
},
{
"epoch": 0.3505535055350554,
"grad_norm": 1.5234375,
"learning_rate": 1.6423761324717636e-05,
"loss": 0.9837,
"step": 380
},
{
"epoch": 0.3551660516605166,
"grad_norm": 1.6328125,
"learning_rate": 1.6299462063008272e-05,
"loss": 0.9645,
"step": 385
},
{
"epoch": 0.35977859778597787,
"grad_norm": 1.5546875,
"learning_rate": 1.61735277755598e-05,
"loss": 0.9743,
"step": 390
},
{
"epoch": 0.3643911439114391,
"grad_norm": 1.671875,
"learning_rate": 1.6045991148623752e-05,
"loss": 0.995,
"step": 395
},
{
"epoch": 0.36900369003690037,
"grad_norm": 1.515625,
"learning_rate": 1.5916885284338937e-05,
"loss": 0.9764,
"step": 400
},
{
"epoch": 0.3736162361623616,
"grad_norm": 1.59375,
"learning_rate": 1.5786243692139826e-05,
"loss": 0.9795,
"step": 405
},
{
"epoch": 0.37822878228782286,
"grad_norm": 1.4921875,
"learning_rate": 1.5654100280059155e-05,
"loss": 0.9689,
"step": 410
},
{
"epoch": 0.3828413284132841,
"grad_norm": 1.546875,
"learning_rate": 1.5520489345927095e-05,
"loss": 0.9614,
"step": 415
},
{
"epoch": 0.3874538745387454,
"grad_norm": 1.5234375,
"learning_rate": 1.538544556846925e-05,
"loss": 1.0044,
"step": 420
},
{
"epoch": 0.39206642066420666,
"grad_norm": 1.59375,
"learning_rate": 1.5249003998305787e-05,
"loss": 0.9729,
"step": 425
},
{
"epoch": 0.3966789667896679,
"grad_norm": 1.5859375,
"learning_rate": 1.5111200048854055e-05,
"loss": 0.9791,
"step": 430
},
{
"epoch": 0.40129151291512916,
"grad_norm": 1.4765625,
"learning_rate": 1.4972069487137024e-05,
"loss": 0.9591,
"step": 435
},
{
"epoch": 0.4059040590405904,
"grad_norm": 1.5234375,
"learning_rate": 1.4831648424499953e-05,
"loss": 0.9754,
"step": 440
},
{
"epoch": 0.41051660516605165,
"grad_norm": 1.578125,
"learning_rate": 1.4689973307237687e-05,
"loss": 0.9727,
"step": 445
},
{
"epoch": 0.4151291512915129,
"grad_norm": 1.5390625,
"learning_rate": 1.4547080907135024e-05,
"loss": 0.9824,
"step": 450
},
{
"epoch": 0.41974169741697415,
"grad_norm": 1.5390625,
"learning_rate": 1.4403008311922593e-05,
"loss": 0.9607,
"step": 455
},
{
"epoch": 0.42435424354243545,
"grad_norm": 1.46875,
"learning_rate": 1.4257792915650728e-05,
"loss": 0.9599,
"step": 460
},
{
"epoch": 0.4289667896678967,
"grad_norm": 1.5859375,
"learning_rate": 1.4111472408983843e-05,
"loss": 0.9719,
"step": 465
},
{
"epoch": 0.43357933579335795,
"grad_norm": 1.453125,
"learning_rate": 1.3964084769417823e-05,
"loss": 0.9854,
"step": 470
},
{
"epoch": 0.4381918819188192,
"grad_norm": 1.4765625,
"learning_rate": 1.3815668251422953e-05,
"loss": 0.9788,
"step": 475
},
{
"epoch": 0.44280442804428044,
"grad_norm": 1.4921875,
"learning_rate": 1.3666261376514978e-05,
"loss": 0.9657,
"step": 480
},
{
"epoch": 0.4474169741697417,
"grad_norm": 1.53125,
"learning_rate": 1.3515902923256832e-05,
"loss": 0.9858,
"step": 485
},
{
"epoch": 0.45202952029520294,
"grad_norm": 1.4765625,
"learning_rate": 1.3364631917193671e-05,
"loss": 0.9622,
"step": 490
},
{
"epoch": 0.4566420664206642,
"grad_norm": 1.421875,
"learning_rate": 1.321248762072377e-05,
"loss": 0.9479,
"step": 495
},
{
"epoch": 0.4612546125461255,
"grad_norm": 1.546875,
"learning_rate": 1.3059509522907998e-05,
"loss": 0.9815,
"step": 500
},
{
"epoch": 0.46586715867158673,
"grad_norm": 1.578125,
"learning_rate": 1.2905737329220394e-05,
"loss": 0.9563,
"step": 505
},
{
"epoch": 0.470479704797048,
"grad_norm": 1.4375,
"learning_rate": 1.2751210951242636e-05,
"loss": 0.9721,
"step": 510
},
{
"epoch": 0.47509225092250923,
"grad_norm": 1.453125,
"learning_rate": 1.2595970496304975e-05,
"loss": 0.9779,
"step": 515
},
{
"epoch": 0.4797047970479705,
"grad_norm": 1.515625,
"learning_rate": 1.2440056257076376e-05,
"loss": 0.9673,
"step": 520
},
{
"epoch": 0.4843173431734317,
"grad_norm": 1.5,
"learning_rate": 1.2283508701106559e-05,
"loss": 0.9489,
"step": 525
},
{
"epoch": 0.488929889298893,
"grad_norm": 1.453125,
"learning_rate": 1.2126368460322637e-05,
"loss": 0.9617,
"step": 530
},
{
"epoch": 0.4935424354243542,
"grad_norm": 1.515625,
"learning_rate": 1.1968676320483103e-05,
"loss": 0.9461,
"step": 535
},
{
"epoch": 0.4981549815498155,
"grad_norm": 1.5078125,
"learning_rate": 1.1810473210591882e-05,
"loss": 0.9585,
"step": 540
},
{
"epoch": 0.5027675276752768,
"grad_norm": 1.4765625,
"learning_rate": 1.1651800192275197e-05,
"loss": 0.9486,
"step": 545
},
{
"epoch": 0.507380073800738,
"grad_norm": 1.46875,
"learning_rate": 1.1492698449124042e-05,
"loss": 0.9542,
"step": 550
},
{
"epoch": 0.5119926199261993,
"grad_norm": 1.5234375,
"learning_rate": 1.1333209276004959e-05,
"loss": 0.9625,
"step": 555
},
{
"epoch": 0.5166051660516605,
"grad_norm": 1.4296875,
"learning_rate": 1.1173374068341962e-05,
"loss": 0.9515,
"step": 560
},
{
"epoch": 0.5212177121771218,
"grad_norm": 1.4296875,
"learning_rate": 1.1013234311372353e-05,
"loss": 0.9493,
"step": 565
},
{
"epoch": 0.525830258302583,
"grad_norm": 1.4375,
"learning_rate": 1.0852831569379217e-05,
"loss": 0.9454,
"step": 570
},
{
"epoch": 0.5304428044280443,
"grad_norm": 1.4921875,
"learning_rate": 1.0692207474903421e-05,
"loss": 0.9468,
"step": 575
},
{
"epoch": 0.5350553505535055,
"grad_norm": 2.28125,
"learning_rate": 1.0531403717937888e-05,
"loss": 0.9472,
"step": 580
},
{
"epoch": 0.5396678966789668,
"grad_norm": 1.5234375,
"learning_rate": 1.037046203510694e-05,
"loss": 0.9462,
"step": 585
},
{
"epoch": 0.544280442804428,
"grad_norm": 1.4921875,
"learning_rate": 1.0209424198833571e-05,
"loss": 0.937,
"step": 590
},
{
"epoch": 0.5488929889298892,
"grad_norm": 1.4765625,
"learning_rate": 1.0048332006497406e-05,
"loss": 0.9625,
"step": 595
},
{
"epoch": 0.5535055350553506,
"grad_norm": 1.8671875,
"learning_rate": 9.887227269586184e-06,
"loss": 0.9425,
"step": 600
},
{
"epoch": 0.5581180811808119,
"grad_norm": 1.6171875,
"learning_rate": 9.7261518028436e-06,
"loss": 0.9484,
"step": 605
},
{
"epoch": 0.5627306273062731,
"grad_norm": 1.4140625,
"learning_rate": 9.565147413416266e-06,
"loss": 0.9589,
"step": 610
},
{
"epoch": 0.5673431734317343,
"grad_norm": 1.40625,
"learning_rate": 9.404255890002677e-06,
"loss": 0.9426,
"step": 615
},
{
"epoch": 0.5719557195571956,
"grad_norm": 1.6484375,
"learning_rate": 9.243518992006944e-06,
"loss": 0.9522,
"step": 620
},
{
"epoch": 0.5765682656826568,
"grad_norm": 1.4375,
"learning_rate": 9.082978438700138e-06,
"loss": 0.94,
"step": 625
},
{
"epoch": 0.5811808118081181,
"grad_norm": 1.59375,
"learning_rate": 8.922675898392072e-06,
"loss": 0.948,
"step": 630
},
{
"epoch": 0.5857933579335793,
"grad_norm": 1.453125,
"learning_rate": 8.762652977616258e-06,
"loss": 0.9565,
"step": 635
},
{
"epoch": 0.5904059040590406,
"grad_norm": 1.4609375,
"learning_rate": 8.602951210330942e-06,
"loss": 0.9567,
"step": 640
},
{
"epoch": 0.5950184501845018,
"grad_norm": 1.3828125,
"learning_rate": 8.443612047138965e-06,
"loss": 0.9339,
"step": 645
},
{
"epoch": 0.5996309963099631,
"grad_norm": 1.4140625,
"learning_rate": 8.284676844529258e-06,
"loss": 0.9524,
"step": 650
},
{
"epoch": 0.6042435424354243,
"grad_norm": 1.6171875,
"learning_rate": 8.126186854142752e-06,
"loss": 0.9452,
"step": 655
},
{
"epoch": 0.6088560885608856,
"grad_norm": 1.4140625,
"learning_rate": 7.968183212065537e-06,
"loss": 0.9364,
"step": 660
},
{
"epoch": 0.6134686346863468,
"grad_norm": 1.34375,
"learning_rate": 7.81070692815195e-06,
"loss": 0.9459,
"step": 665
},
{
"epoch": 0.6180811808118081,
"grad_norm": 1.421875,
"learning_rate": 7.6537988753805e-06,
"loss": 0.9495,
"step": 670
},
{
"epoch": 0.6226937269372693,
"grad_norm": 1.4140625,
"learning_rate": 7.497499779245268e-06,
"loss": 0.9438,
"step": 675
},
{
"epoch": 0.6273062730627307,
"grad_norm": 1.4140625,
"learning_rate": 7.3418502071856004e-06,
"loss": 0.9412,
"step": 680
},
{
"epoch": 0.6319188191881919,
"grad_norm": 1.515625,
"learning_rate": 7.186890558056836e-06,
"loss": 0.9412,
"step": 685
},
{
"epoch": 0.6365313653136532,
"grad_norm": 1.3828125,
"learning_rate": 7.0326610516447825e-06,
"loss": 0.9371,
"step": 690
},
{
"epoch": 0.6411439114391144,
"grad_norm": 1.390625,
"learning_rate": 6.879201718226658e-06,
"loss": 0.9513,
"step": 695
},
{
"epoch": 0.6457564575645757,
"grad_norm": 1.390625,
"learning_rate": 6.7265523881812335e-06,
"loss": 0.9204,
"step": 700
},
{
"epoch": 0.6503690036900369,
"grad_norm": 1.4765625,
"learning_rate": 6.574752681650864e-06,
"loss": 0.9189,
"step": 705
},
{
"epoch": 0.6549815498154982,
"grad_norm": 1.34375,
"learning_rate": 6.423841998258069e-06,
"loss": 0.9241,
"step": 710
},
{
"epoch": 0.6595940959409594,
"grad_norm": 1.359375,
"learning_rate": 6.273859506879365e-06,
"loss": 0.9394,
"step": 715
},
{
"epoch": 0.6642066420664207,
"grad_norm": 1.4296875,
"learning_rate": 6.124844135478971e-06,
"loss": 0.94,
"step": 720
},
{
"epoch": 0.6688191881918819,
"grad_norm": 1.375,
"learning_rate": 5.976834561005069e-06,
"loss": 0.9276,
"step": 725
},
{
"epoch": 0.6734317343173432,
"grad_norm": 1.40625,
"learning_rate": 5.829869199351188e-06,
"loss": 0.9286,
"step": 730
},
{
"epoch": 0.6780442804428044,
"grad_norm": 1.3359375,
"learning_rate": 5.68398619538536e-06,
"loss": 0.9322,
"step": 735
},
{
"epoch": 0.6826568265682657,
"grad_norm": 1.40625,
"learning_rate": 5.53922341304961e-06,
"loss": 0.9341,
"step": 740
},
{
"epoch": 0.6872693726937269,
"grad_norm": 1.3359375,
"learning_rate": 5.39561842553239e-06,
"loss": 0.9368,
"step": 745
},
{
"epoch": 0.6918819188191881,
"grad_norm": 1.359375,
"learning_rate": 5.2532085055164205e-06,
"loss": 0.9278,
"step": 750
},
{
"epoch": 0.6964944649446494,
"grad_norm": 1.4375,
"learning_rate": 5.112030615504601e-06,
"loss": 0.9409,
"step": 755
},
{
"epoch": 0.7011070110701108,
"grad_norm": 1.796875,
"learning_rate": 4.972121398226371e-06,
"loss": 0.9344,
"step": 760
},
{
"epoch": 0.705719557195572,
"grad_norm": 1.3828125,
"learning_rate": 4.833517167127077e-06,
"loss": 0.9374,
"step": 765
},
{
"epoch": 0.7103321033210332,
"grad_norm": 1.375,
"learning_rate": 4.6962538969428416e-06,
"loss": 0.9322,
"step": 770
},
{
"epoch": 0.7149446494464945,
"grad_norm": 1.34375,
"learning_rate": 4.560367214363295e-06,
"loss": 0.923,
"step": 775
},
{
"epoch": 0.7195571955719557,
"grad_norm": 1.3671875,
"learning_rate": 4.425892388784681e-06,
"loss": 0.9261,
"step": 780
},
{
"epoch": 0.724169741697417,
"grad_norm": 1.3125,
"learning_rate": 4.292864323155684e-06,
"loss": 0.9257,
"step": 785
},
{
"epoch": 0.7287822878228782,
"grad_norm": 1.34375,
"learning_rate": 4.161317544918345e-06,
"loss": 0.9368,
"step": 790
},
{
"epoch": 0.7333948339483395,
"grad_norm": 1.375,
"learning_rate": 4.031286197046493e-06,
"loss": 0.9208,
"step": 795
},
{
"epoch": 0.7380073800738007,
"grad_norm": 1.3125,
"learning_rate": 3.902804029183907e-06,
"loss": 0.9122,
"step": 800
},
{
"epoch": 0.742619926199262,
"grad_norm": 1.359375,
"learning_rate": 3.775904388884618e-06,
"loss": 0.944,
"step": 805
},
{
"epoch": 0.7472324723247232,
"grad_norm": 1.359375,
"learning_rate": 3.650620212957524e-06,
"loss": 0.9647,
"step": 810
},
{
"epoch": 0.7518450184501845,
"grad_norm": 1.3828125,
"learning_rate": 3.5269840189176616e-06,
"loss": 0.9427,
"step": 815
},
{
"epoch": 0.7564575645756457,
"grad_norm": 1.3203125,
"learning_rate": 3.405027896546277e-06,
"loss": 0.9404,
"step": 820
},
{
"epoch": 0.761070110701107,
"grad_norm": 1.359375,
"learning_rate": 3.2847834995619067e-06,
"loss": 0.9241,
"step": 825
},
{
"epoch": 0.7656826568265682,
"grad_norm": 1.4140625,
"learning_rate": 3.1662820374046776e-06,
"loss": 0.9318,
"step": 830
},
{
"epoch": 0.7702952029520295,
"grad_norm": 1.3984375,
"learning_rate": 3.0495542671358745e-06,
"loss": 0.9397,
"step": 835
},
{
"epoch": 0.7749077490774908,
"grad_norm": 1.3359375,
"learning_rate": 2.934630485454948e-06,
"loss": 0.951,
"step": 840
},
{
"epoch": 0.7795202952029521,
"grad_norm": 1.359375,
"learning_rate": 2.8215405208360237e-06,
"loss": 0.9213,
"step": 845
},
{
"epoch": 0.7841328413284133,
"grad_norm": 1.328125,
"learning_rate": 2.7103137257858867e-06,
"loss": 0.9285,
"step": 850
},
{
"epoch": 0.7887453874538746,
"grad_norm": 1.3515625,
"learning_rate": 2.600978969225558e-06,
"loss": 0.9279,
"step": 855
},
{
"epoch": 0.7933579335793358,
"grad_norm": 1.3515625,
"learning_rate": 2.493564628997369e-06,
"loss": 0.9264,
"step": 860
},
{
"epoch": 0.7979704797047971,
"grad_norm": 1.328125,
"learning_rate": 2.3880985844994674e-06,
"loss": 0.9252,
"step": 865
},
{
"epoch": 0.8025830258302583,
"grad_norm": 1.40625,
"learning_rate": 2.284608209449746e-06,
"loss": 0.9317,
"step": 870
},
{
"epoch": 0.8071955719557196,
"grad_norm": 1.3359375,
"learning_rate": 2.183120364780975e-06,
"loss": 0.932,
"step": 875
},
{
"epoch": 0.8118081180811808,
"grad_norm": 1.375,
"learning_rate": 2.083661391669043e-06,
"loss": 0.9271,
"step": 880
},
{
"epoch": 0.816420664206642,
"grad_norm": 1.359375,
"learning_rate": 1.986257104696121e-06,
"loss": 0.9285,
"step": 885
},
{
"epoch": 0.8210332103321033,
"grad_norm": 1.390625,
"learning_rate": 1.8909327851504633e-06,
"loss": 0.9239,
"step": 890
},
{
"epoch": 0.8256457564575646,
"grad_norm": 1.3984375,
"learning_rate": 1.7977131744646724e-06,
"loss": 0.9446,
"step": 895
},
{
"epoch": 0.8302583025830258,
"grad_norm": 1.3515625,
"learning_rate": 1.7066224677940313e-06,
"loss": 0.9313,
"step": 900
},
{
"epoch": 0.834870848708487,
"grad_norm": 1.4140625,
"learning_rate": 1.6176843077366755e-06,
"loss": 0.9322,
"step": 905
},
{
"epoch": 0.8394833948339483,
"grad_norm": 1.328125,
"learning_rate": 1.5309217781971419e-06,
"loss": 0.9215,
"step": 910
},
{
"epoch": 0.8440959409594095,
"grad_norm": 1.359375,
"learning_rate": 1.446357398394934e-06,
"loss": 0.9346,
"step": 915
},
{
"epoch": 0.8487084870848709,
"grad_norm": 1.3125,
"learning_rate": 1.3640131170196758e-06,
"loss": 0.9262,
"step": 920
},
{
"epoch": 0.8533210332103321,
"grad_norm": 1.375,
"learning_rate": 1.2839103065343084e-06,
"loss": 0.9368,
"step": 925
},
{
"epoch": 0.8579335793357934,
"grad_norm": 1.34375,
"learning_rate": 1.2060697576278812e-06,
"loss": 0.9278,
"step": 930
},
{
"epoch": 0.8625461254612546,
"grad_norm": 1.3515625,
"learning_rate": 1.1305116738193211e-06,
"loss": 0.9175,
"step": 935
},
{
"epoch": 0.8671586715867159,
"grad_norm": 1.3125,
"learning_rate": 1.0572556662136036e-06,
"loss": 0.9119,
"step": 940
},
{
"epoch": 0.8717712177121771,
"grad_norm": 1.328125,
"learning_rate": 9.863207484116987e-07,
"loss": 0.9363,
"step": 945
},
{
"epoch": 0.8763837638376384,
"grad_norm": 1.328125,
"learning_rate": 9.177253315755796e-07,
"loss": 0.9398,
"step": 950
},
{
"epoch": 0.8809963099630996,
"grad_norm": 1.328125,
"learning_rate": 8.514872196496182e-07,
"loss": 0.911,
"step": 955
},
{
"epoch": 0.8856088560885609,
"grad_norm": 1.328125,
"learning_rate": 7.876236047395525e-07,
"loss": 0.9333,
"step": 960
},
{
"epoch": 0.8902214022140221,
"grad_norm": 1.3671875,
"learning_rate": 7.26151062650291e-07,
"loss": 0.9341,
"step": 965
},
{
"epoch": 0.8948339483394834,
"grad_norm": 1.3671875,
"learning_rate": 6.670855485836525e-07,
"loss": 0.9374,
"step": 970
},
{
"epoch": 0.8994464944649446,
"grad_norm": 1.3359375,
"learning_rate": 6.104423929971948e-07,
"loss": 0.9168,
"step": 975
},
{
"epoch": 0.9040590405904059,
"grad_norm": 1.3828125,
"learning_rate": 5.562362976251901e-07,
"loss": 0.943,
"step": 980
},
{
"epoch": 0.9086715867158671,
"grad_norm": 1.4453125,
"learning_rate": 5.044813316627994e-07,
"loss": 0.9292,
"step": 985
},
{
"epoch": 0.9132841328413284,
"grad_norm": 1.421875,
"learning_rate": 4.5519092811439627e-07,
"loss": 0.9345,
"step": 990
},
{
"epoch": 0.9178966789667896,
"grad_norm": 1.34375,
"learning_rate": 4.083778803070504e-07,
"loss": 0.9388,
"step": 995
},
{
"epoch": 0.922509225092251,
"grad_norm": 1.328125,
"learning_rate": 3.6405433856999684e-07,
"loss": 0.9202,
"step": 1000
},
{
"epoch": 0.9271217712177122,
"grad_norm": 1.390625,
"learning_rate": 3.2223180708102933e-07,
"loss": 0.9415,
"step": 1005
},
{
"epoch": 0.9317343173431735,
"grad_norm": 1.46875,
"learning_rate": 2.829211408805932e-07,
"loss": 0.9408,
"step": 1010
},
{
"epoch": 0.9363468634686347,
"grad_norm": 1.328125,
"learning_rate": 2.461325430543482e-07,
"loss": 0.9233,
"step": 1015
},
{
"epoch": 0.940959409594096,
"grad_norm": 1.5859375,
"learning_rate": 2.1187556208496885e-07,
"loss": 0.9262,
"step": 1020
},
{
"epoch": 0.9455719557195572,
"grad_norm": 1.359375,
"learning_rate": 1.8015908937382587e-07,
"loss": 0.9326,
"step": 1025
},
{
"epoch": 0.9501845018450185,
"grad_norm": 1.3671875,
"learning_rate": 1.5099135693322776e-07,
"loss": 0.9176,
"step": 1030
},
{
"epoch": 0.9547970479704797,
"grad_norm": 1.3984375,
"learning_rate": 1.2437993524979984e-07,
"loss": 0.9394,
"step": 1035
},
{
"epoch": 0.959409594095941,
"grad_norm": 1.375,
"learning_rate": 1.0033173131956175e-07,
"loss": 0.9187,
"step": 1040
},
{
"epoch": 0.9640221402214022,
"grad_norm": 1.359375,
"learning_rate": 7.885298685522235e-08,
"loss": 0.932,
"step": 1045
},
{
"epoch": 0.9686346863468634,
"grad_norm": 1.359375,
"learning_rate": 5.99492766661347e-08,
"loss": 0.9416,
"step": 1050
},
{
"epoch": 0.9732472324723247,
"grad_norm": 1.34375,
"learning_rate": 4.362550721136338e-08,
"loss": 0.9411,
"step": 1055
},
{
"epoch": 0.977859778597786,
"grad_norm": 1.3671875,
"learning_rate": 2.988591532620322e-08,
"loss": 0.9285,
"step": 1060
},
{
"epoch": 0.9824723247232472,
"grad_norm": 1.328125,
"learning_rate": 1.8734067122514464e-08,
"loss": 0.9281,
"step": 1065
},
{
"epoch": 0.9870848708487084,
"grad_norm": 1.3125,
"learning_rate": 1.0172857063137643e-08,
"loss": 0.9352,
"step": 1070
},
{
"epoch": 0.9916974169741697,
"grad_norm": 1.34375,
"learning_rate": 4.204507210633368e-09,
"loss": 0.9315,
"step": 1075
},
{
"epoch": 0.996309963099631,
"grad_norm": 1.390625,
"learning_rate": 8.30566650548148e-10,
"loss": 0.9198,
"step": 1080
},
{
"epoch": 1.0,
"eval_loss": 0.9405834078788757,
"eval_runtime": 138.721,
"eval_samples_per_second": 110.654,
"eval_steps_per_second": 1.73,
"step": 1084
},
{
"epoch": 1.0,
"step": 1084,
"total_flos": 1.515445781320958e+18,
"train_loss": 0.6863565506530424,
"train_runtime": 5790.4174,
"train_samples_per_second": 23.951,
"train_steps_per_second": 0.187
}
],
"logging_steps": 5,
"max_steps": 1084,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 100,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1.515445781320958e+18,
"train_batch_size": 16,
"trial_name": null,
"trial_params": null
}